Electronic apparatus and method to train neural network to determine defective air conditioner

Patent metadata

Field	Value
Publication number	US-11920807-B2
Application number	US-202117428125-A
Country	US
Kind code	B2
Filing date	Jul 27, 2021
Priority date	Aug 20, 2020
Publication date	Mar 5, 2024
Grant date	Mar 5, 2024

Abstract

An electronic apparatus is provided. The electronic apparatus includes a communication interface, a memory, and a processor. The processor according to the disclosure is configured to acquire weather information and information on a space where an air conditioner is installed, train a neural network model based on the weather information and the information on the space, based on acquiring driving information of the air conditioner and a measured temperature of the space through the communication interface, input the measured temperature of the space and the external temperature into the neural network model and acquire predicted temperature information per time for the space, determine whether a defect exists in the air conditioner based on the predicted temperature information and the measured temperature of the space, and based on determining that a defect exists in the air conditioner, generate a notification signal.

First claim

What is claimed is:

1. An electronic apparatus controlling an air conditioner comprising:
a communication interface;
a memory storing at least one instruction; and
a processor,
wherein, when the at least one instruction is executed by the processor, the processor is configured to:
acquire weather information comprising an external temperature of a region where the air conditioner is installed and information on a space comprising a temperature of the space where the air conditioner is installed,
train a neural network model based on the weather information and the information on the space, where the information on the space includes information on a type of use of the space where the air conditioner is installed, information on a location within a building in which the space exists, information on a number and size of windows present in the space, and a number of occupants of the space,
based on acquiring driving information of the air conditioner comprising a set temperature and the acquired temperature of the space through the communication interface, input the acquired temperature of the space and the external temperature into the neural network model and acquire predicted temperature information per time for the space,
determine whether a defect exists in the air conditioner based on a difference between the predicted temperature information of the neural network model and the acquired temperature of the space, and

based on determining that a defect exists in the air conditioner, generate a notification signal,
wherein, when the at least one instruction is executed by the processor, the processor is further configured to:
acquire a heat characteristic for the space based on the acquired temperature of the space and the external temperature, and
correct the predicted temperature information based on the heat characteristic, and

wherein the heat characteristic comprises a temperature distribution for the space where the air conditioner is installed.

2. The electronic apparatus of claim 1 , wherein, when the at least one instruction is executed by the processor, the processor is further configured to:
acquire a predicted time point when the temperature of the space reaches the set temperature based on the predicted temperature information and the set temperature; and
based on the acquired temperature of the space not reaching the set temperature within a predetermined time range from the predicted time point, determine that a defect exists in the air conditioner.

3. The electronic apparatus of claim 1 , wherein, when the at least one instruction is executed by the processor, the processor is further configured to:
acquire a predicted time point when the temperature of the space reaches the set temperature based on the predicted temperature information and the set temperature, and
based on a difference between the acquired temperature of the space and the set temperature being greater than or equal to a predetermined value at the predicted time point, determine that a defect exists in the air conditioner.

4. The electronic apparatus of claim 1 , wherein, when the at least one instruction is executed by the processor, the processor is further configured to:
acquire a prestored neural network model trained to acquire predicted temperature information per time for the space based on the temperature of the space and the external temperature in the memory, and
train the neural network model by updating a parameter of the prestored neural network model based on the weather information, the information on the space, and information on a use pattern.

5. The electronic apparatus of claim 1 , wherein the processor is configured to:
based on determining that a defect does not exist in the air conditioner, retrain the neural network model based on the temperature of the space, the external temperature, and the predicted temperature information.

6. The electronic apparatus of claim 1 , wherein the information on the space comprises:
at least one of a use of the space and a size of the space, a location of the air conditioner inside the space, a number of windows present in the space, the sizes of the windows, or whether the windows are opened and closed.

7. The electronic apparatus of claim 1 , wherein the driving information comprises:
at least one of the set temperature, a wind volume, or a driving mode.

8. The electronic apparatus of claim 1 , wherein, when the at least one instruction is executed by the processor, the processor is further configured to:
control the communication interface to transmit the notification signal for providing a notification message to a user terminal.

9. The electronic apparatus of claim 1 , wherein, when the at least one instruction is executed by the processor, the processor is further configured to:
acquire information on a use pattern of the air conditioner, and
train the neural network model based on the information on the use pattern of the air conditioner.

10. A method for controlling an electronic apparatus controlling an air conditioner, the method comprising:
acquiring weather information comprising an external temperature of a region where the air conditioner is installed and information on a space comprising a temperature of the space where the air conditioner is installed;
training a neural network model based on the weather information and the information on the space, where the information on the space includes information on a type of use of the space where the air conditioner is installed, information on a location within a building in which the space exists, information on a number and size of windows present in the space, and a number of occupants of the space;
based on acquiring driving information of the air conditioner comprising a set temperature and the acquired temperature of the space through a communication interface, inputting the acquired temperature of the space and the external temperature into the neural network model and acquiring predicted temperature information per time for the space;
determining whether a defect exists in the air conditioner based on a difference between the predicted temperature information of the neural network model and the acquired temperature of the space; and
based on determining that a defect exists in the air conditioner, generating a notification signal,
wherein the acquiring predicted temperature information comprises:
acquiring a heat characteristic for the space based on the acquired temperature of the space and the external temperature, and
correcting the predicted temperature information based on the heat characteristic, and

wherein the heat characteristic comprises a temperature distribution for the space where the air conditioner is installed.

11. The method of claim 10 , wherein the determining comprises:
acquiring a predicted time point when the temperature of the space reaches the set temperature based on the predicted temperature information and the set temperature; and
based on the acquired temperature of the space not reaching the set temperature within a predetermined time range from the predicted time point, determining that a defect exists in the air conditioner.

12. The method of claim 10 , wherein the determining comprises:
acquiring a predicted time point when the temperature of the space reaches the set temperature based on the predicted temperature information and the set temperature; and
based on a difference between the acquired temperature of the space and the set temperature being greater than or equal to a predetermined value at the predicted time point, determining that a defect exists in the air conditioner.

Assignees

• Samsung Electronics Co Ltd

Inventors

• Song Sunggeun
• Kim Kyungjae
• Song Kwanwoo
• Lee Jehyeon
• Cho Hyejung

Classifications

• F24F11/38 Primary

  Failure diagnosis · CPC title

• F24F11/52

  Indication arrangements, e.g. displays · CPC title

• F24F11/64

  using pre-stored data · CPC title

• F24F2110/12

  of the outside air · CPC title

• F24F2130/10

  Weather information or forecasts · CPC title